LendingTree has developed a multi-agent mortgage assistant using Amazon Bedrock to help users navigate the complexities of home buying. The assistant educates borrowers, understands their financial situation, and provides tailored mortgage options through natural conversation. Borrowers must consider various factors, including loan types, terms, and rates, along with industry-specific jargon like 'discount points' and 'debt-to-income ratio.' This complexity often leaves users feeling overwhelmed before they even start the home-buying process. LendingTree has been assisting consumers with mortgage decisions for over 25 years, connecting millions of people with lenders to find competitive offers. The AI-powered assistant represents the next step in this mission, ensuring accurate, transparent, and secure guidance for users. The solution must meet the same high standards that have guided LendingTree since its inception, including compliance with regulatory requirements and robust data protection. Operating within the mortgage industry’s regulatory framework requires content filtering, personal identifiable information (PII) protection, and compliance oversight, all of which are non-negotiable. This made Amazon Bedrock and its built-in guardrails the ideal foundation for the solution. 'Our goal was to be a trusted partner in the home-buying journey, a guide that educates consumers, understands their situation, and matches them with the right offer. The foundation models and built-in guardrails in Amazon Bedrock let us deliver that with security and compliance from the start.' — Srinivas Madabushi, SVP Technology, LendingTree
To address these challenges, LendingTree deployed three independent AI agents: a supervisor and two specialized workers (education and matching), coordinated using LangGraph, the Model Context Protocol (MCP), and foundation models powered by Amazon Bedrock. All agents run containerized services on Amazon Elastic Container Service (Amazon ECS) with AWS Fargate. LendingTree chose Amazon Bedrock for its multi-model flexibility and inherited AWS governance controls, which their compliance team required. The solution was deployed on Amazon ECS instead of Amazon Bedrock AgentCore because it was already in production when AgentCore reached general availability. AgentCore is a platform to build, connect, and optimize agents at scale, with any framework or model. The following figure shows the high-level architecture.
LendingTree multi-agent architecture for mortgage guidance (1) The consumer-facing chat interface is a React application running as a containerized service on Amazon ECS with Fargate, serving consumers on web and mobile browsers through a public endpoint. (2) User inputs and model outputs pass through Amazon Bedrock Guardrails for content filtering (such as hate and profanity detection) and PII redaction. Incoming messages are also screened for prompt threats. In parallel with Guardrails, a safety classifier based on a large language model (LLM) enforces LendingTree’s conversational policy. The two safety checks run concurrently, so this added assurance doesn’t add latency. A business-logic layer handles LendingTree’s operational rules: routing complex issues to human support and redirecting off-topic conversations.
Source: awsml
